Related papers: Diversity Enhanced Table-to-Text Generation via Ty…
Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world…
This systematic review undertakes a comprehensive analysis of current research on data-to-text generation, identifying gaps, challenges, and future directions within the field. Relevant literature in this field on datasets, evaluation…
In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically,…
Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the base autoregressive…
Digital learning platforms enable students to learn on a flexible and individual schedule as well as providing instant feedback mechanisms. The field of STEM education requires students to solve numerous training exercises to grasp…
There has been a recent explosion in applications for dialogue interaction ranging from direction-giving and tourist information to interactive story systems. Yet the natural language generation (NLG) component for many of these systems…
Pre-trained language models (PLM) have achieved remarkable advancement in table-to-text generation tasks. However, the lack of labeled domain-specific knowledge and the topology gap between tabular data and text make it difficult for PLMs…
Heterogenity of data-to-text generation datasets limits the research on data-to-text generation systems. We present TabGenie - a toolkit which enables researchers to explore, preprocess, and analyze a variety of data-to-text generation…
Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that are less informative but highly factual, or more informative…
Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…
Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and…
Transformer-based language models have shown to be very powerful for natural language generation (NLG). However, text generation conditioned on some user inputs, such as topics or attributes, is non-trivial. Past approach relies on either…
Table-to-text generation, a long-standing challenge in natural language generation, has remained unexplored through the lens of subjectivity. Subjectivity here encompasses the comprehension of information derived from the table that cannot…
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…
Efficient querying and analysis of large tabular datasets remain significant challenges, especially for users without expertise in programming languages like SQL. Text-to-SQL approaches have shown promising performance on benchmark data;…
We present a hybrid statistical and grammar-based system for surface natural language generation (NLG) that uses grammar rules, conditions on using those grammar rules, and corpus statistics to determine the word order. We also describe how…
Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions to this verification challenge often…
Natural Language Generation systems typically have two parts - strategic ('what to say') and tactical ('how to say'). We present our experiments in building an unsupervised corpus-driven template based tactical NLG system. We consider…
Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However,…
Natural-language generation (NLG) techniques can be used to automatically produce technical documentation from a domain knowledge base and linguistic and contextual models. We discuss this application of NLG technology from both a technical…